feat: phase 1 of AI pipeline hardening — single LLM client + tier-aware models

Implements phase 1 of AI_PIPELINE_HARDENING_PLAN.md. Every Anthropic call
now goes through one module that owns retry, timeout, abort, structured-
output parsing, schema validation, and best-effort call telemetry.

* src/lib/llm.js — single callLLM entry point. Resolves model per tier
  (fast / standard / reasoning) with admin:model legacy fallback for the
  standard tier; 60s default timeout via AbortController; balanced-brace
  JSON extraction; LLMHttpError, LLMTruncatedError, LLMOutputError, and
  LLMValidationError surface clearly distinct failure modes.
* src/lib/llmRetry.js — exponential backoff with full jitter, retries
  only on transient HTTP statuses, honours Retry-After up to 60s, never
  retries on AbortError.
* src/lib/llmSchemas.js — Zod schemas for every structured task plus
  normalizeHandbookResult (collapses legacy "executes" relations into
  the canonical "executed_by" vocabulary).
* src/lib/api.js — thin shim over callLLM so existing callers (extraction
  pipeline, learning, quiz, R42, knowledge graph) keep working unchanged.
* src/lib/__tests__/ — 32 Vitest cases covering parse paths, error
  surfaces, simulation mode, model resolution, and schema validation.
* src/pages/Admin/index.jsx — three model inputs (fast / standard /
  reasoning) replacing the single legacy field; legacy value falls back
  for the standard tier so existing overrides survive.

Adds Zod and Vitest, plus an "npm run test" script.

Also cleans up the pre-existing repo-wide ESLint failures so phase 1's
"npm run lint passes" acceptance criterion can be checked: drops unused
React imports across the JSX tree (React 19 JSX runtime auto-imports),
attaches cause to rethrown errors in the service modules, ignores
pb_migrations in the ESLint config (PocketBase JSVM globals), and
removes one dead handleCreateCustom function in Leren.jsx. A real
behaviour bug surfaced in Testen.jsx — the quiz timer captured a stale
finishQuiz via setInterval closure; now updated via finishQuizRef so the
timer always invokes the latest callback.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

src/lib/learningService.js

@@ -1,6 +1,6 @@
 import { anthropicApi } from './api';
 import * as db from './db';
-import { getCurriculumTopic, getCurriculumYear } from './curriculumService';
+import { getCurriculumTopic } from './curriculumService';
 
 const CONTENT_GENERATION_SYSTEM = `You are an expert learning content writer for Respellion, an internal IT company.
 You write training material for employees based on knowledge topics.
@@ -138,7 +138,7 @@ ${instructions}`;
     const jsonMatch = responseText.match(/\{[\s\S]*\}/);
     newContent = JSON.parse(jsonMatch ? jsonMatch[0] : responseText);
   } catch (e) {
-    throw new Error('AI could not generate valid learning content. Please try again.');
+    throw new Error('AI could not generate valid learning content. Please try again.', { cause: e });
   }
 
   const mergedContent = { ...(cached || {}), ...newContent };
@@ -165,7 +165,7 @@ Apply the refinement and return the complete updated JSON object using the same
     const jsonMatch = responseText.match(/\{[\s\S]*\}/);
     content = JSON.parse(jsonMatch ? jsonMatch[0] : responseText);
   } catch (e) {
-    throw new Error('AI could not process the refinement. Please try a different instruction.');
+    throw new Error('AI could not process the refinement. Please try a different instruction.', { cause: e });
   }
 
   await db.setContent(topic.id, content);
@@ -198,7 +198,7 @@ Return ONLY a JSON object with this structure:
     newTopic = JSON.parse(jsonMatch ? jsonMatch[0] : responseText);
     newTopic.id = 'custom_' + Date.now().toString(36);
   } catch (e) {
-    throw new Error('Could not process custom topic. Please try again.');
+    throw new Error('Could not process custom topic. Please try again.', { cause: e });
   }
 
   await db.upsertTopic(newTopic);